A multi-expose fusion image dehazing based on scene depth information

Haze weather can lead to reduced visibility of captured images, affecting daily production and life. In this paper, a new defogging technique for multi-exposure images combined with prior algorithm is proposed. Firstly, the transmittance of different regions of the haze image is calculated to obtain more accurate prior information. Secondly, gamma correction is applied to the prior map to obtain a set of multiple underexposure images. Thirdly, for the difference between global features and local details in image defogging, the multiple underexposure image set is decomposed into base and detail layers using guided filtering, and the fusion weight maps of the base layers image patches and the detail layers Laplacian decomposition are constructed, respectively. Finally, the haze-free image is reconstructed and restored. The haze image is selected from a standard dataset with different haze concentrations and compared with the commonly used haze removal algorithms. The defogging effect of this algorithm has better performance in visual effect and objective evaluation index.

Automated summary

In this paper, a new defogging technique for multi-exposure images combined with prior algorithm is proposed. The algorithm calculates the transmittance of different regions of the haze image and decomposes and fuses the image using guided filtering. The algorithm has better performance in haze removal.